Browse State-of-the-Art › Few-Shot Class-Incremental Learning
Few-Shot Class-Incremental Learning
55 papers with code · 3 benchmarks · 3 datasets archive 2025-07-28
Benchmarks archive 2025-07-28
3 leaderboard tables shown for this task, 3 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
Syntology 1 newer paper was judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): CIFAR-100 (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
3 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 118 · with a code link: 55 · where Syntology ran a sample: 20 (20 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (20 of 118 tagged: 20 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 2: papers 1 to 100 of 118, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
9 Jan 2025 2 repositories listedTo this end, we propose Continuous Knowledge-Preserving Decomposition for FSCIL (CKPD-FSCIL), a framework that decomposes a model's weights into two parts: one that compacts existing knowledge (knowledge-sensitive…
-
10 Mar 2024 2 repositories listedFew-shot Class-Incremental Learning (FSCIL) poses the challenge of retaining prior knowledge while learning from limited new data streams, all without overfitting.
-
28 Dec 2023 2 repositories listedTo address the above challenges, we introduce the FILP-3D framework with two novel components: the Redundant Feature Eliminator (RFE) for feature space misalignment and the Spatial Noise Compensator (SNC) for…
-
19 Dec 2023 2 repositories listed Syntology official (archive's flag): 2 ran · 11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified (of 15 harvested samples) · 4 pointer-only (licence)Inspired by the Lottery Ticket Hypothesis (LTH), which highlights the existence of efficient subnetworks within larger, dense networks, a high-performing Winning Subnetwork (WSN) in terms of task performance under…
-
3 Aug 2023 2 repositories listed Syntology community repositories only · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)Beyond the normal case, long-tail class incremental learning and few-shot class incremental learning are also proposed to consider the data imbalance and data scarcity, respectively, which are common in real-world…
-
15 Sep 2022 2 repositories listed Syntology official (archive's flag): 5 ran · 7 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified (of 10 harvested samples) · 2 pointer-only (licence)Inspired by Regularized Lottery Ticket Hypothesis (RLTH), which hypothesizes that there exist smooth (non-binary) subnetworks within a dense network that achieve the competitive performance of the dense network, we…
-
30 Mar 2022 2 repositories listed Syntology official (archive's flag): 2 ran · 4 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples)Moreover, it is imperative that such learning must respect certain memory and computational constraints such as (i) training samples are limited to only a few per class, (ii) the computational cost of learning a novel…
-
15 Apr 2025 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)However, current strategies primarily focus on preventing catastrophic forgetting, considering only the relationship between novel and base classes, without paying attention to the specific decision spaces of each class.
-
1 Jan 2025 1 repository listedFew-shot Class-Incremental Learning (FSCIL) challenges models to adapt to new classes with limited samples, presenting greater difficulties than traditional classincremental learning.
-
9 Dec 2024 1 repository listedThen for each cluster, we employ greedy selection strategy to ensure that the Gaussian distribution of the sampled features closely matches the Gaussian distribution of all unlabeled features within the cluster.
-
11 Nov 2024 1 repository listedKnowledge is then distilled back into the GNN through a Graph Knowledge Distillation Module, preserving the model's memory.
-
2 Nov 2024 1 repository listedIn this paper, we aim to mitigate these issues by directly constraining the span of each class distribution from a covariance perspective.
-
11 Oct 2024 1 repository listedThis paper introduces a new method to tackle the Few-Shot Continual Incremental Learning (FSCIL) problem in 3D point cloud environments.
-
8 Oct 2024 1 repository listedBuilding upon the recent efforts for enhancing transferability, such as promoting the spread of features, we find that trying to secure the spread of features within a more confined feature space enables the learned…
-
10 Jul 2024 1 repository listedIn this work, as a complement to existing metrics, we offer a new metric called generalized average accuracy (gAcc) which is designed to provide an extra equitable evaluation by incorporating different perspectives of…
-
8 Jul 2024 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified (of 8 harvested samples) · 8 pointer-only (licence)The dual design enables the model to maintain the robust features of base classes, while adaptively learning distinctive feature shifts for novel classes.
-
27 May 2024 1 repository listed Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 6 unverified (of 15 harvested samples) · 1 pointer-only (licence)Few-shot class-incremental learning (FSCIL) is proposed to continually learn from novel classes with only a few samples after the (pre-)training on base classes with sufficient data.
-
26 May 2024 1 repository listed Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified (of 10 harvested samples)For the first time, we explore few-shot tuning of vision foundation models for class-incremental learning.
-
8 May 2024 1 repository listedThis problem remains an open problem because all recent works are built upon the convolutional neural networks performing sub-optimally compared to the transformer approaches.
-
9 Apr 2024 1 repository listed Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified (of 15 harvested samples) · 8 pointer-only (licence)FSCIL methods start with a many-shot first task to learn a very good feature extractor and then move to the few-shot setting from the second task onwards.
-
2 Apr 2024 1 repository listed Syntology official (archive's flag): 12 ran · 12 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified (of 14 harvested samples) · 1 pointer-only (licence)In this paper, we argue that large models such as vision and language transformers pre-trained on large datasets can be excellent few-shot incremental learners.
-
27 Mar 2024 1 repository listed Syntology official (archive's flag): 6 ran · 6 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 8 harvested samples) · 8 pointer-only (licence)To address these challenges, we propose the OrCo framework built on two core principles: features' orthogonality in the representation space, and contrastive learning.
-
19 Mar 2024 1 repository listedThrough the combined effects of these measures, our network acquires robust NTK properties, ensuring optimal convergence and stability of the NTK matrix and minimizing the NTK-related generalization loss, significantly…
-
14 Mar 2024 1 repository listedFew-Shot Class-Incremental Learning (FSCIL) models aim to incrementally learn new classes with scarce samples while preserving knowledge of old ones.
-
12 Mar 2024 1 repository listedIn this work, we introduce Online Few-Shot Class-Incremental Learning (O-FSCIL), based on a lightweight model consisting of a pretrained and metalearned feature extractor and an expandable explicit memory storing the…
-
26 Jan 2024 1 repository listedIn this paper, we propose a novel approach called Prompt Learning for FSCIL (PL-FSCIL), which harnesses the power of prompts in conjunction with a pre-trained Vision Transformer (ViT) model to address the challenges of…
-
3 Jan 2024 1 repository listedWhen progressing to a new session, pseudo-features are sampled from old-class distributions combined with training images of the current session to optimize the prompt, thus enabling the model to learn new knowledge…
-
8 Dec 2023 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)In this Few-Shot Class-Incremental Learning (FSCIL) scenario, existing methods either introduce extra learnable components or rely on a frozen feature extractor to mitigate catastrophic forgetting and overfitting…
-
31 Oct 2023 1 repository listedMoreover, we design a multi-stage strategy for training S2C model, which mitigates the training challenges posed by limited data in the incremental process.
-
31 Jul 2023 1 repository listedFor most real-world applications, robots need to adapt and learn continually with limited data in their environments.
-
5 Jul 2023 1 repository listed
-
5 Jul 2023 1 repository listed
-
19 Jun 2023 1 repository listed
-
24 Apr 2023 1 repository listed
-
2 Apr 2023 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)
-
27 Mar 2023 1 repository listed
-
8 Mar 2023 1 repository listed
-
6 Feb 2023 1 repository listed
-
2 Feb 2023 1 repository listed
-
24 Jan 2023 1 repository listed
-
1 Jan 2023 1 repository listed
-
1 Jan 2023 1 repository listed
-
10 Oct 2022 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified (of 9 harvested samples) · 1 pointer-only (licence)
-
30 Jul 2022 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 5 harvested samples) · 5 pointer-only (licence)
-
22 Jul 2022 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples)
-
30 May 2022 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 2 samples that ran constructed an object rather than computing a result (of 4 harvested samples) · 4 pointer-only (licence)
-
27 May 2022 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified (of 6 harvested samples)
-
31 Mar 2022 1 repository listed
-
14 Mar 2022 1 repository listed
-
23 Dec 2021 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples)
-
30 Oct 2021 1 repository listed
-
13 Oct 2021 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples)
-
19 Jul 2021 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 2 samples that ran constructed an object rather than computing a result (of 4 harvested samples)
-
7 Apr 2021 1 repository listed Syntology 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified (of 10 harvested samples) · 1 pointer-only (licence)
-
23 Apr 2020 1 repository listed
-
Few-Shot Class-Incremental Learning For Efficient SAR Automatic Target Recognition26 May 2025 0 repositories listed
-
MEGA: Second-Order Gradient Alignment for Catastrophic Forgetting Mitigation in GFSCIL18 Apr 2025 0 repositories listed
-
Adaptive Additive Parameter Updates of Vision Transformers for Few-Shot Continual Learning11 Apr 2025 0 repositories listed
-
Diffusion Meets Few-shot Class Incremental Learning30 Mar 2025 0 repositories listed
-
Learn by Reasoning: Analogical Weight Generation for Few-Shot Class-Incremental Learning27 Mar 2025 0 repositories listed
-
An experimental approach on Few Shot Class Incremental Learning14 Mar 2025 0 repositories listed
-
A New Benchmark for Few-Shot Class-Incremental Learning: Redefining the Upper Bound13 Mar 2025 0 repositories listed
-
Singular Value Fine-tuning for Few-Shot Class-Incremental Learning13 Mar 2025 0 repositories listed
-
FSCIL-SEI: Few-Shot Class-Incremental Learning Approach for Specific Emitter Identification3 Mar 2025 0 repositories listed
-
Brain-inspired analogical mixture prototypes for few-shot class-incremental learning26 Feb 2025 0 repositories listed
-
Latest Advancements Towards Catastrophic Forgetting under Data Scarcity: A Comprehensive Survey on Few-Shot Class Incremental Learning12 Feb 2025 0 repositories listed
-
Controllable Forgetting Mechanism for Few-Shot Class-Incremental Learning27 Jan 2025 0 repositories listed
-
Strategic Base Representation Learning via Feature Augmentations for Few-Shot Class Incremental Learning16 Jan 2025 0 repositories listed
-
Language-Inspired Relation Transfer for Few-shot Class-Incremental Learning10 Jan 2025 0 repositories listed
-
Attraction Diminishing and Distributing for Few-Shot Class-Incremental Learning1 Jan 2025 0 repositories listed
-
Hyperbolic Uncertainty-Aware Few-Shot Incremental Point Cloud Segmentation1 Jan 2025 0 repositories listed
-
SEC-Prompt:SEmantic Complementary Prompting for Few-Shot Class-Incremental Learning1 Jan 2025 0 repositories listed
-
Tripartite Weight-Space Ensemble for Few-Shot Class-Incremental Learning1 Jan 2025 0 repositories listed
-
Breaking Fine-Grained Classification Barriers with Cost-Free Data in Few-Shot Class-Incremental Learning29 Dec 2024 0 repositories listed
-
AnchorInv: Few-Shot Class-Incremental Learning of Physiological Signals via Representation Space Guided Inversion18 Dec 2024 0 repositories listed
-
CALA: A Class-Aware Logit Adapter for Few-Shot Class-Incremental Learning17 Dec 2024 0 repositories listed
-
On Distilling the Displacement Knowledge for Few-Shot Class-Incremental Learning15 Dec 2024 0 repositories listed
-
Embedding Space Allocation with Angle-Norm Joint Classifiers for Few-Shot Class-Incremental Learning14 Nov 2024 0 repositories listed
-
Inductive Graph Few-shot Class Incremental Learning11 Nov 2024 0 repositories listed
-
Few-Shot Class-Incremental Learning with Non-IID Decentralized Data18 Sep 2024 0 repositories listed
-
Knowledge Adaptation Network for Few-Shot Class-Incremental Learning18 Sep 2024 0 repositories listed
-
Towards Robust Few-shot Class Incremental Learning in Audio Classification using Contrastive Representation27 Jul 2024 0 repositories listed
-
Delve into Base-Novel Confusion: Redundancy Exploration for Few-Shot Class-Incremental Learning8 May 2024 0 repositories listed
-
Few Shot Class Incremental Learning using Vision-Language models2 May 2024 0 repositories listed
-
21 Mar 2024 0 repositories listed
-
Controllable Relation Disentanglement for Few-Shot Class-Incremental Learning17 Mar 2024 0 repositories listed
-
Contrastive Augmented Graph2Graph Memory Interaction for Few Shot Continual Learning7 Mar 2024 0 repositories listed
-
Few-Shot Class-Incremental Learning with Prior Knowledge2 Feb 2024 0 repositories listed
-
Bias Mitigating Few-Shot Class-Incremental Learning1 Feb 2024 0 repositories listed
-
Enhanced Few-Shot Class-Incremental Learning via Ensemble Models14 Jan 2024 0 repositories listed
-
TLCE: Transfer-Learning Based Classifier Ensembles for Few-Shot Class-Incremental Learning7 Dec 2023 0 repositories listed
-
Evaluating Pretrained models for Deployable Lifelong Learning22 Nov 2023 0 repositories listed
-
Aggregated f-average Neural Network for Interpretable Ensembling9 Oct 2023 0 repositories listed
-
Image-Object-Specific Prompt Learning for Few-Shot Class-Incremental Learning6 Sep 2023 0 repositories listed
-
Few-shot Class-incremental Learning for Classification and Object Detection: A Survey13 Aug 2023 0 repositories listed
-
Balanced Supervised Contrastive Learning for Few-Shot Class-Incremental Learning26 May 2023 0 repositories listed
-
Evolving Dictionary Representation for Few-shot Class-incremental Learning3 May 2023 0 repositories listed
-
A Survey on Few-Shot Class-Incremental Learning17 Apr 2023 0 repositories listed
-
Few-shot Class-incremental Learning for Cross-domain Disease Classification12 Apr 2023 0 repositories listed
-
MASIL: Towards Maximum Separable Class Representation for Few Shot Class Incremental Learning8 Apr 2023 0 repositories listed
Syntology lines on 22 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections